metadata
base_model: meta-llama/Llama-2-7b-hf
datasets:
- yihanwang617/WizardLM_70k_processed_indicator_unfiltered_4k
library_name: peft
license: llama2
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: llama-2-qlora-wizard-processed-indicator-0.6
results: []
llama-2-qlora-wizard-processed-indicator-0.6
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the yihanwang617/WizardLM_70k_processed_indicator_unfiltered_4k dataset. It achieves the following results on the evaluation set:
- Loss: 0.6296
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.693 | 0.2225 | 200 | 0.6798 |
| 0.6836 | 0.4450 | 400 | 0.6580 |
| 0.683 | 0.6675 | 600 | 0.6481 |
| 0.6654 | 0.8900 | 800 | 0.6413 |
| 0.6446 | 1.1125 | 1000 | 0.6380 |
| 0.629 | 1.3350 | 1200 | 0.6334 |
| 0.6241 | 1.5575 | 1400 | 0.6312 |
| 0.6087 | 1.7800 | 1600 | 0.6299 |
Framework versions
- PEFT 0.12.0
- Transformers 4.40.1
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1